© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5588
    Prev
    Next
    INDEX
    Explanations

    mentions of time in schedules and treatment plans

    oai_token-act-pair · gemini-2.0-flash

    references to days and time periods

    np_token-act-pair-logits · gpt-4o-mini

    days of the week

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.82
    ритори
    -0.65
     GoogleFonts
    -0.63
     estekak
    -0.59
    RectangleBorder
    -0.54
     autob
    -0.54
     inflater
    -0.54
    PhysRevD
    -0.53
    Népesség
    -0.53
     hcm
    -0.53
    POSITIVE LOGITS
     Monday
    1.27
     everyday
    1.21
     day
    1.18
    Monday
    1.18
     days
    1.15
     seven
    1.13
    days
    1.10
     daily
    1.10
     Days
    1.07
    day
    1.06
    Activations Density 1.836%

    No Known Activations